{"id":"https://openalex.org/W7213284547","doi":"https://doi.org/10.64898/2026.09.14.26363036","title":"Interpretable Trajectory-Based Feature Extraction from Longitudinal Electronic Health Records","display_name":"Interpretable Trajectory-Based Feature Extraction from Longitudinal Electronic Health Records","publication_year":2026,"publication_date":"2026-09-15","ids":{"openalex":"https://openalex.org/W7213284547","doi":"https://doi.org/10.64898/2026.09.14.26363036"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.14.26363036","doi":"https://doi.org/10.64898/2026.09.14.26363036","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.26363036","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/15/2026.09.14.26363036.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/15/2026.09.14.26363036.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123857644","display_name":"Vitaly Bulgakov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I48633490","display_name":"Mass General Brigham","ror":"https://ror.org/04py2rh25","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Vitaly Bulgakov","raw_affiliation_strings":["Mass General Brigham, Boston, USA","Profiteya LLC, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mass General Brigham, Boston, USA","institution_ids":["https://openalex.org/I48633490"]},{"raw_affiliation_string":"Profiteya LLC, Boston, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083393697","display_name":"Alexander Turchin","orcid":"https://orcid.org/0000-0002-8609-564X","observed_orcids":["https://orcid.org/0000-0002-8609-564X"]},"institutions":[{"id":"https://openalex.org/I48633490","display_name":"Mass General Brigham","ror":"https://ror.org/04py2rh25","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I48633490"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Turchin","raw_affiliation_strings":["Mass General Brigham, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mass General Brigham, Boston, USA","institution_ids":["https://openalex.org/I48633490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5123857644"],"corresponding_institution_ids":["https://openalex.org/I48633490"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10350","display_name":"Electronic Health Records Systems","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/model-interpretability","display_name":"model interpretability","score":0.847000002861023},{"id":"https://openalex.org/keywords/longitudinal-electronic-health-records","display_name":"longitudinal electronic health records","score":0.9929999709129333},{"id":"https://openalex.org/keywords/l1-regularized-logistic-regression","display_name":"L1-regularized logistic regression","score":0.8270000219345093},{"id":"https://openalex.org/keywords/sparse-feature-selection","display_name":"sparse feature selection","score":0.8579999804496765},{"id":"https://openalex.org/keywords/in-hospital-mortality-prediction","display_name":"in-hospital mortality prediction","score":0.9359999895095825},{"id":"https://openalex.org/keywords/30-day-readmission","display_name":"30-day readmission","score":0.8410000205039978},{"id":"https://openalex.org/keywords/icu-mortality","display_name":"ICU mortality","score":0.8259999752044678},{"id":"https://openalex.org/keywords/mimic-iv","display_name":"MIMIC-IV","score":0.8489999771118164}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.916100025177002},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8129000067710876},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7595000267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5486999750137329},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49300000071525574},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.4779999852180481},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4178999960422516},{"id":"https://openalex.org/C3019952477","wikidata":"https://www.wikidata.org/wiki/Q1324077","display_name":"Health records","level":3,"score":0.4025000035762787},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C3020672099","wikidata":"https://www.wikidata.org/wiki/Q857354","display_name":"Longitudinal data","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36320000886917114},{"id":"https://openalex.org/C2777895361","wikidata":"https://www.wikidata.org/wiki/Q1758614","display_name":"Longitudinal study","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3296999931335449},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.3165999948978424},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.14.26363036","doi":"https://doi.org/10.64898/2026.09.14.26363036","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.26363036","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/15/2026.09.14.26363036.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.14.26363036","doi":"https://doi.org/10.64898/2026.09.14.26363036","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.14.26363036","pdf_url":"https://www.medrxiv.org/content/medrxiv/early/2026/09/15/2026.09.14.26363036.full.pdf","source":{"id":"https://openalex.org/S3005729997","display_name":"medRxiv","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310315909"],"host_organization_lineage_names":["Cold Spring Harbor Laboratory Press"],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"medRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.9537000060081482}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213284547.pdf","grobid_xml":"https://content.openalex.org/works/W7213284547.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W1142362541","https://openalex.org/W2963092154","https://openalex.org/W2999937291","https://openalex.org/W4210458679","https://openalex.org/W4224316420","https://openalex.org/W4313439128","https://openalex.org/W4315926964","https://openalex.org/W4416055050","https://openalex.org/W7126274747","https://openalex.org/W7138144355","https://openalex.org/W7172401153"],"related_works":["https://openalex.org/W4309227547","https://openalex.org/W4381715289","https://openalex.org/W2897007327","https://openalex.org/W4249685443","https://openalex.org/W4313478901","https://openalex.org/W7202139931","https://openalex.org/W4416551700","https://openalex.org/W2923493534","https://openalex.org/W4417123830","https://openalex.org/W4416133959"],"abstract_inverted_index":{"Abstract":[0],"Longitudinal":[1],"electronic":[2],"health":[3],"records":[4],"(EHRs)":[5],"contain":[6],"rich":[7],"information":[8,165],"about":[9],"the":[10,161,169,192,197],"evolution":[11,274],"of":[12,113,163,172,178,196,272],"a":[13,183,262],"patient\u2019s":[14],"clinical":[15,75],"state,":[16],"but":[17],"temporal":[18,58,250],"measurements":[19],"and":[20,70,96,99,110,115,136,168,205,219,247,264,275],"events":[21,76],"are":[22,60,77,91,156,200],"often":[23],"represented":[24,61,78],"using":[25,101,123,202],"summary":[26],"statistics":[27],"or":[28,86,284],"complex":[29],"learned":[30],"representations":[31,211],"that":[32,46,223,237],"can":[33,242,276],"be":[34,243,277],"difficult":[35],"to":[36,153,158],"interpret":[37],"clinically.":[38],"We":[39],"propose":[40],"an":[41],"interpretable":[42,80,249,270],"trajectory-based":[43],"feature":[44,108],"representation":[45],"transforms":[47],"heterogeneous":[48,238],"longitudinal":[49,164,239],"EHR":[50,240],"data":[51],"into":[52,245],"compact,":[53],"human-readable":[54],"predictive":[55,117,229,255,288],"features.":[56,118,174],"Numerical":[57],"variables":[59],"by":[62,79],"trajectory":[63,89,173,225,282],"states":[64,81],"such":[65],"as":[66],"INCREASING,":[67],"DECREASING":[68],",":[69,72],"STABLE":[71],"while":[73,252],"categorical":[74,207],"describing":[82],"repeated":[83],"occurrence,":[84],"stability,":[85],"change.":[87],"These":[88],"features":[90,251],"combined":[92],"with":[93,182,279,286],"static":[94],"patient":[95,273],"encounter":[97],"characteristics":[98],"evaluated":[100,122,201],"L1-regularized":[102],"logistic":[103],"regression,":[104],"which":[105],"provides":[106,227,261],"sparse":[107],"selection":[109],"direct":[111],"identification":[112],"positive":[114],"negative":[116],"The":[119,175,209,234,257],"approach":[120,266],"is":[121,180],"MIMIC-IV":[124],"in":[125,231],"two":[126,210],"clinically":[127,269],"distinct":[128],"prediction":[129,167],"tasks:":[130],"in-hospital":[131],"mortality":[132],"following":[133],"ICU":[134,145],"admission":[135],"hospital":[137],"readmission":[138],"within":[139],"30":[140],"days":[141],"after":[142],"discharge.":[143],"For":[144,187],"mortality,":[146],"multiple":[147],"observation":[148,185],"windows":[149],"ranging":[150],"from":[151,191],"1":[152],"48":[154],"hours":[155,195],"investigated":[157],"examine":[159],"how":[160],"availability":[162],"affects":[166],"relative":[170],"contribution":[171],"highest":[176],"AUROC":[177],"0.8751":[179],"obtained":[181],"32-hour":[184],"window.":[186],"30-day":[188],"readmission,":[189],"trajectories":[190],"final":[193],"72":[194],"index":[198],"hospitalization":[199],"both":[203],"three-state":[204],"five-state":[206],"representations.":[208],"produce":[212],"essentially":[213],"identical":[214],"discriminative":[215],"performance":[216],"(AUROC":[217],"0.6875":[218],"0.6876,":[220],"respectively),":[221],"indicating":[222],"increasing":[224],"granularity":[226],"little":[228],"benefit":[230],"this":[232],"setting.":[233],"results":[235],"demonstrate":[236],"observations":[241],"transformed":[244],"compact":[246],"directly":[248],"retaining":[253],"useful":[254],"information.":[256],"proposed":[258],"framework":[259],"therefore":[260],"simple":[263],"model-compatible":[265],"for":[267],"identifying":[268],"patterns":[271],"extended":[278],"more":[280],"detailed":[281],"definitions":[283],"applied":[285],"other":[287],"models.":[289]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-09-16T00:00:00"}